>       Tapping a PCIe signal should be doable, but it would take some
> serious engineering at the electrical level.  What I'd try is to tap the
> transmission line with a 3-arm T attenuator, with most of the power passing
> straight through, and a greatly attenuated signal coming out the side arm. 
> Then terminate the side arm, and amplify back to standard logic levels for
> compatibility with a logic analyzer.  The tap adapter would have to be
> implemented as a microwave PC board, with connectors to plug between the
> device and the cable.

Let's call yours as an analog tap.

I think you can make a digital one too - place an LVDS receiver, then
divide the signal to 2 directions, one for LVDS transmiter (pass-thru
path) and the other one to the data recorder device. This setup goes
num_lanes x 2 times (for each direction) and +1 for the reference clock.
It should require only a standard PCB (with differential lines). The
thing I would be most worried about here is the delay introduced by the
tapping component (e.g. a small FPGA sitting between the mobo and the card).

D.
_______________________________________________
Open-graphics mailing list
[email protected]
http://lists.duskglow.com/mailman/listinfo/open-graphics
List service provided by Duskglow Consulting, LLC (www.duskglow.com)

Reply via email to